{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JCOV3ZKOYHNBQ6Z5GLMWKPQ3JU","short_pith_number":"pith:JCOV3ZKO","canonical_record":{"source":{"id":"2412.12735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T09:57:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0fbccf90d4a57afce4e5bb9875dc475557e55f97e68145229a47cae56f7e9a61","abstract_canon_sha256":"56c537bd75143e10f9dc17bea98989aa49da1facde6393377d1f13f593155040"},"schema_version":"1.0"},"canonical_sha256":"489d5de54ec1da187b3d32d9653e1b4d1bbb71e3f096713e7e420e5da2a69453","source":{"kind":"arxiv","id":"2412.12735","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12735","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12735v1","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12735","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"pith_short_12","alias_value":"JCOV3ZKOYHNB","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"pith_short_16","alias_value":"JCOV3ZKOYHNBQ6Z5","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"pith_short_8","alias_value":"JCOV3ZKO","created_at":"2026-07-05T09:50:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JCOV3ZKOYHNBQ6Z5GLMWKPQ3JU","target":"record","payload":{"canonical_record":{"source":{"id":"2412.12735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T09:57:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0fbccf90d4a57afce4e5bb9875dc475557e55f97e68145229a47cae56f7e9a61","abstract_canon_sha256":"56c537bd75143e10f9dc17bea98989aa49da1facde6393377d1f13f593155040"},"schema_version":"1.0"},"canonical_sha256":"489d5de54ec1da187b3d32d9653e1b4d1bbb71e3f096713e7e420e5da2a69453","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:19.911687Z","signature_b64":"6udVZZ96V52UjtkLvVbHrBZ/mT3z6hefPf65RPT3goyzWZmGFjV7wws9YuBfiAiJiJVNnEagM3f7tygmBqzyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"489d5de54ec1da187b3d32d9653e1b4d1bbb71e3f096713e7e420e5da2a69453","last_reissued_at":"2026-07-05T09:50:19.911260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:19.911260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.12735","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:50:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kM7Ii6Pjy9KKnRoQoyrWxNeFEeZHEt1zKsqUlL5hutE2uU3xFfgfAj3JUR45Zy1yEvo8I0hKQj1kKjVL3/fBCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T18:35:21.870136Z"},"content_sha256":"d2024ba524b8c3f86ac2a3683afbabc05084fe5164a1bd2acd46603c3dcc532c","schema_version":"1.0","event_id":"sha256:d2024ba524b8c3f86ac2a3683afbabc05084fe5164a1bd2acd46603c3dcc532c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JCOV3ZKOYHNBQ6Z5GLMWKPQ3JU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GIRAFFE: Design Choices for Extending the Context Length of Visual Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Lei Li, Mukai Li, Qi Liu, Shansan Gong","submitted_at":"2024-12-17T09:57:21Z","abstract_excerpt":"Visual Language Models (VLMs) demonstrate impressive capabilities in processing multimodal inputs, yet applications such as visual agents, which require handling multiple images and high-resolution videos, demand enhanced long-range modeling. Moreover, existing open-source VLMs lack systematic exploration into extending their context length, and commercial models often provide limited details. To tackle this, we aim to establish an effective solution that enhances long context performance of VLMs while preserving their capacities in short context scenarios. Towards this goal, we make the best "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12735","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.12735/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:50:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"busUHpijJwU7HCsoIOul6H62pqvktglKH0M3LHjMRE+rIJaI55PGlLHPbvUUWhKkp9ntw+vnu1zDfVaJ0FDGCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T18:35:21.871182Z"},"content_sha256":"5a7a891d89e4e50e6e5639ac9b469e650e5d1e7d3a01bd51286275b7c7c0533d","schema_version":"1.0","event_id":"sha256:5a7a891d89e4e50e6e5639ac9b469e650e5d1e7d3a01bd51286275b7c7c0533d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JCOV3ZKOYHNBQ6Z5GLMWKPQ3JU/bundle.json","state_url":"https://pith.science/pith/JCOV3ZKOYHNBQ6Z5GLMWKPQ3JU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JCOV3ZKOYHNBQ6Z5GLMWKPQ3JU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T18:35:21Z","links":{"resolver":"https://pith.science/pith/JCOV3ZKOYHNBQ6Z5GLMWKPQ3JU","bundle":"https://pith.science/pith/JCOV3ZKOYHNBQ6Z5GLMWKPQ3JU/bundle.json","state":"https://pith.science/pith/JCOV3ZKOYHNBQ6Z5GLMWKPQ3JU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JCOV3ZKOYHNBQ6Z5GLMWKPQ3JU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JCOV3ZKOYHNBQ6Z5GLMWKPQ3JU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"56c537bd75143e10f9dc17bea98989aa49da1facde6393377d1f13f593155040","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T09:57:21Z","title_canon_sha256":"0fbccf90d4a57afce4e5bb9875dc475557e55f97e68145229a47cae56f7e9a61"},"schema_version":"1.0","source":{"id":"2412.12735","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12735","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12735v1","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12735","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"pith_short_12","alias_value":"JCOV3ZKOYHNB","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"pith_short_16","alias_value":"JCOV3ZKOYHNBQ6Z5","created_at":"2026-07-05T09:50:19Z"},{"alias_kind":"pith_short_8","alias_value":"JCOV3ZKO","created_at":"2026-07-05T09:50:19Z"}],"graph_snapshots":[{"event_id":"sha256:5a7a891d89e4e50e6e5639ac9b469e650e5d1e7d3a01bd51286275b7c7c0533d","target":"graph","created_at":"2026-07-05T09:50:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.12735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Language Models (VLMs) demonstrate impressive capabilities in processing multimodal inputs, yet applications such as visual agents, which require handling multiple images and high-resolution videos, demand enhanced long-range modeling. Moreover, existing open-source VLMs lack systematic exploration into extending their context length, and commercial models often provide limited details. To tackle this, we aim to establish an effective solution that enhances long context performance of VLMs while preserving their capacities in short context scenarios. Towards this goal, we make the best ","authors_text":"Lei Li, Mukai Li, Qi Liu, Shansan Gong","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T09:57:21Z","title":"GIRAFFE: Design Choices for Extending the Context Length of Visual Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12735","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d2024ba524b8c3f86ac2a3683afbabc05084fe5164a1bd2acd46603c3dcc532c","target":"record","created_at":"2026-07-05T09:50:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"56c537bd75143e10f9dc17bea98989aa49da1facde6393377d1f13f593155040","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T09:57:21Z","title_canon_sha256":"0fbccf90d4a57afce4e5bb9875dc475557e55f97e68145229a47cae56f7e9a61"},"schema_version":"1.0","source":{"id":"2412.12735","kind":"arxiv","version":1}},"canonical_sha256":"489d5de54ec1da187b3d32d9653e1b4d1bbb71e3f096713e7e420e5da2a69453","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"489d5de54ec1da187b3d32d9653e1b4d1bbb71e3f096713e7e420e5da2a69453","first_computed_at":"2026-07-05T09:50:19.911260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:19.911260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6udVZZ96V52UjtkLvVbHrBZ/mT3z6hefPf65RPT3goyzWZmGFjV7wws9YuBfiAiJiJVNnEagM3f7tygmBqzyCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:19.911687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12735","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2024ba524b8c3f86ac2a3683afbabc05084fe5164a1bd2acd46603c3dcc532c","sha256:5a7a891d89e4e50e6e5639ac9b469e650e5d1e7d3a01bd51286275b7c7c0533d"],"state_sha256":"49b62be9118605bfb7549b358ff8b405179adef9ba9b76f878eb5582635c889f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KndnqdEQc3ScOKJtylMw/NZZRiuIaOMSvDY0NoRlhyBBLXykZnsJUg4d9UPJcOhfrMncG0fdDLSscHpSPeWFBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T18:35:21.877592Z","bundle_sha256":"2dc58bc01206093b64f6a0a98b0cb9345226db2644701304f848a7c7abd08feb"}}